Hugging Face's logo

swespot
/
matplotlib-sft-v0

Safetensors
qwen3
Model card Files
xet
 Community
colin commited on
Commit
8a9c73c
·
verified ·
1 Parent(s): c567bb3

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. args.json +669 -0
  4. chat_template.jinja +61 -0
  5. config.json +69 -0
  6. merges.txt +0 -0
  7. model-00001-of-00002.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model.safetensors.index.json +405 -0
  10. special_tokens_map.json +31 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +239 -0
  13. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
args.json ADDED
@@ -0,0 +1,669 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "use_ray": false,
3
+ "ray_exp_name": null,
4
+ "device_groups": null,
5
+ "model": "Qwen/Qwen3-4B-Instruct-2507",
6
+ "model_type": "qwen3_nothinking",
7
+ "model_revision": null,
8
+ "task_type": "causal_lm",
9
+ "torch_dtype": "bfloat16",
10
+ "attn_impl": null,
11
+ "new_special_tokens": [],
12
+ "num_labels": null,
13
+ "problem_type": null,
14
+ "rope_scaling": null,
15
+ "device_map": null,
16
+ "max_memory": {},
17
+ "max_model_len": null,
18
+ "local_repo_path": null,
19
+ "init_strategy": null,
20
+ "template": "qwen3_nothinking",
21
+ "system": null,
22
+ "max_length": 32768,
23
+ "truncation_strategy": "left",
24
+ "max_pixels": null,
25
+ "agent_template": null,
26
+ "norm_bbox": null,
27
+ "use_chat_template": true,
28
+ "padding_free": true,
29
+ "padding_side": "right",
30
+ "loss_scale": "default",
31
+ "sequence_parallel_size": 1,
32
+ "response_prefix": null,
33
+ "template_backend": "swift",
34
+ "dataset": [
35
+ "/data/repotune/data/agentic/bugfix/matplotlib_20201231_5b89c9c/v0/sft_all.jsonl#2048",
36
+ "/data/repotune/data/agentic/fim/matplotlib_20201231_5b89c9c/v0/sft_all.jsonl#2048",
37
+ "/data/repotune/data/agentic/testgen/matplotlib_20201231_5b89c9c/v0/sft_all.jsonl#2048",
38
+ "/data/repotune/data/agentic/ar/matplotlib_20201231_5b89c9c/sft_all.jsonl#2048"
39
+ ],
40
+ "val_dataset": [
41
+ "/data/repotune/data/val/django_e13b714/sbv_msa_gemini25pro.jsonl",
42
+ "/data/repotune/data/val/django_e13b714/sbv_msa_gemini3pro.jsonl"
43
+ ],
44
+ "cached_dataset": [],
45
+ "cached_val_dataset": [],
46
+ "split_dataset_ratio": 0.0,
47
+ "data_seed": 42,
48
+ "dataset_num_proc": 16,
49
+ "load_from_cache_file": true,
50
+ "dataset_shuffle": true,
51
+ "val_dataset_shuffle": false,
52
+ "streaming": false,
53
+ "interleave_prob": null,
54
+ "stopping_strategy": "first_exhausted",
55
+ "shuffle_buffer_size": 1000,
56
+ "download_mode": "reuse_dataset_if_exists",
57
+ "columns": {},
58
+ "strict": false,
59
+ "remove_unused_columns": true,
60
+ "model_name": null,
61
+ "model_author": null,
62
+ "custom_dataset_info": [],
63
+ "quant_method": null,
64
+ "quant_bits": null,
65
+ "hqq_axis": null,
66
+ "bnb_4bit_compute_dtype": "bfloat16",
67
+ "bnb_4bit_quant_type": "nf4",
68
+ "bnb_4bit_use_double_quant": true,
69
+ "bnb_4bit_quant_storage": null,
70
+ "max_new_tokens": null,
71
+ "temperature": null,
72
+ "top_k": 50,
73
+ "top_p": 0.9,
74
+ "repetition_penalty": 1.0,
75
+ "num_beams": 1,
76
+ "stream": false,
77
+ "stop_words": [],
78
+ "logprobs": false,
79
+ "top_logprobs": null,
80
+ "ckpt_dir": null,
81
+ "lora_modules": [],
82
+ "tuner_backend": "peft",
83
+ "train_type": "full",
84
+ "adapters": [],
85
+ "external_plugins": [],
86
+ "seed": 42,
87
+ "model_kwargs": {},
88
+ "load_args": false,
89
+ "load_data_args": false,
90
+ "packing": false,
91
+ "packing_length": null,
92
+ "packing_num_proc": 1,
93
+ "lazy_tokenize": false,
94
+ "custom_register_path": [],
95
+ "use_hf": true,
96
+ "hub_token": null,
97
+ "ddp_timeout": 18000000,
98
+ "ddp_backend": null,
99
+ "ignore_args_error": false,
100
+ "use_swift_lora": false,
101
+ "freeze_llm": false,
102
+ "freeze_vit": true,
103
+ "freeze_aligner": true,
104
+ "freeze_parameters": [],
105
+ "freeze_parameters_regex": null,
106
+ "freeze_parameters_ratio": 0.0,
107
+ "trainable_parameters": [],
108
+ "trainable_parameters_regex": null,
109
+ "adapter_load": null,
110
+ "target_modules": [
111
+ "all-linear"
112
+ ],
113
+ "target_regex": null,
114
+ "modules_to_save": [],
115
+ "lora_rank": 8,
116
+ "lora_alpha": 32,
117
+ "lora_dropout": 0.05,
118
+ "lora_bias": "none",
119
+ "lora_dtype": null,
120
+ "use_rslora": false,
121
+ "rlhf_type": null,
122
+ "ref_load": null,
123
+ "ref_adapter_load": null,
124
+ "beta": 0.1,
125
+ "rpo_alpha": null,
126
+ "reference_free": false,
127
+ "label_smoothing": 0.0,
128
+ "f_divergence_type": "reverse_kl",
129
+ "loss_type": null,
130
+ "desirable_weight": 1.0,
131
+ "undesirable_weight": 1.0,
132
+ "calculate_KL": null,
133
+ "center_rewards_coefficient": null,
134
+ "generation_batch_size": null,
135
+ "steps_per_generation": null,
136
+ "num_generations": 8,
137
+ "num_generations_eval": null,
138
+ "max_completion_length": 512,
139
+ "importance_sampling_level": "token",
140
+ "tau_pos": 1.0,
141
+ "tau_neg": 1.05,
142
+ "epsilon": 0.2,
143
+ "epsilon_high": null,
144
+ "delta": null,
145
+ "use_vllm": true,
146
+ "vllm_mode": null,
147
+ "vllm_enable_prefix_caching": true,
148
+ "vllm_gpu_memory_utilization": 0.9,
149
+ "vllm_tensor_parallel_size": 1,
150
+ "vllm_max_model_len": null,
151
+ "vllm_enforce_eager": false,
152
+ "vllm_limit_mm_per_prompt": null,
153
+ "vllm_disable_cascade_attn": false,
154
+ "vllm_max_num_seqs": null,
155
+ "vllm_mm_processor_cache_gb": null,
156
+ "vllm_engine_kwargs": null,
157
+ "sleep_level": 0,
158
+ "offload_optimizer": false,
159
+ "offload_model": false,
160
+ "offload_bridge": false,
161
+ "vllm_server_base_url": null,
162
+ "vllm_server_host": null,
163
+ "vllm_server_port": [
164
+ 8000
165
+ ],
166
+ "vllm_server_timeout": 240.0,
167
+ "vllm_server_group_port": null,
168
+ "reward_funcs": [],
169
+ "reward_weights": null,
170
+ "cosine_min_len_value_wrong": -0.5,
171
+ "cosine_max_len_value_wrong": 0.0,
172
+ "cosine_min_len_value_correct": 1.0,
173
+ "cosine_max_len_value_correct": 0.5,
174
+ "cosine_max_len": null,
175
+ "repetition_n_grams": 3,
176
+ "repetition_max_penalty": -1.0,
177
+ "soft_max_length": null,
178
+ "soft_cache_length": null,
179
+ "dynamic_sample": false,
180
+ "max_resample_times": 3,
181
+ "overlong_filter": false,
182
+ "scale_rewards": "group",
183
+ "advantage_estimator": "grpo",
184
+ "kl_in_reward": false,
185
+ "wandb_log_unique_prompts": null,
186
+ "log_completions": false,
187
+ "rollout_importance_sampling_mode": null,
188
+ "rollout_importance_sampling_threshold": 2.0,
189
+ "log_rollout_offpolicy_metrics": false,
190
+ "off_policy_sequence_mask_delta": null,
191
+ "reward_model": null,
192
+ "reward_model_plugin": null,
193
+ "sync_ref_model": false,
194
+ "ref_model_sync_steps": 512,
195
+ "ref_model_mixup_alpha": 0.6,
196
+ "async_generate": false,
197
+ "move_model_batches": null,
198
+ "multi_turn_scheduler": null,
199
+ "max_turns": null,
200
+ "completion_length_limit_scope": "per_round",
201
+ "vllm_server_pass_dataset": false,
202
+ "log_entropy": false,
203
+ "top_entropy_quantile": 1.0,
204
+ "num_iterations": 1,
205
+ "check_model": true,
206
+ "padded_vocab_size": 151936,
207
+ "initialize_embedding": false,
208
+ "mlp_padding_free": false,
209
+ "load_safetensors": true,
210
+ "save_safetensors": true,
211
+ "ref_model": null,
212
+ "ref_adapters": [],
213
+ "merge_lora": true,
214
+ "max_shard_size": "5GB",
215
+ "train_dataloader_shuffle": true,
216
+ "dataloader_pin_memory": true,
217
+ "dataloader_persistent_workers": true,
218
+ "dataloader_prefetch_factor": 10,
219
+ "architectures": "Qwen3ForCausalLM",
220
+ "llm_architectures": "Qwen3ForCausalLM",
221
+ "max_epochs": 2,
222
+ "enable_dft_loss": false,
223
+ "enable_channel_loss": false,
224
+ "save_strategy": "steps",
225
+ "original_max_position_embeddings": null,
226
+ "partial_rotary_factor": null,
227
+ "use_shared_expert_gate": false,
228
+ "vit_gradient_checkpointing": true,
229
+ "vit_lr": null,
230
+ "aligner_lr": null,
231
+ "gradient_checkpointing_kwargs": null,
232
+ "linear_num_value_heads": null,
233
+ "linear_num_key_heads": null,
234
+ "linear_key_head_dim": null,
235
+ "linear_value_head_dim": null,
236
+ "linear_conv_kernel_dim": null,
237
+ "layer_types": null,
238
+ "mrope_interleaved": false,
239
+ "micro_batch_size": 1,
240
+ "global_batch_size": 16,
241
+ "recompute_granularity": "full",
242
+ "recompute_method": "uniform",
243
+ "recompute_num_layers": 1,
244
+ "recompute_modules": [
245
+ "core_attn"
246
+ ],
247
+ "use_cpu_initialization": false,
248
+ "deterministic_mode": false,
249
+ "train_iters": null,
250
+ "log_interval": 1,
251
+ "tensorboard_dir": "/data/repotune/train/outputs/mix/mix_8k_bfta_matplotlib_qwen34i_32k_2ep_v0/v0-20260122-012219/runs",
252
+ "no_masked_softmax_fusion": false,
253
+ "no_bias_dropout_fusion": false,
254
+ "no_bias_swiglu_fusion": false,
255
+ "no_rope_fusion": false,
256
+ "no_gradient_accumulation_fusion": false,
257
+ "cross_entropy_loss_fusion": true,
258
+ "cross_entropy_fusion_impl": "native",
259
+ "calculate_per_token_loss": true,
260
+ "use_flash_attn": false,
261
+ "attention_backend": "flash",
262
+ "optimizer": "adam",
263
+ "optimizer_cpu_offload": false,
264
+ "optimizer_offload_fraction": 1.0,
265
+ "use_precision_aware_optimizer": false,
266
+ "main_grads_dtype": "fp32",
267
+ "main_params_dtype": "fp32",
268
+ "exp_avg_dtype": "fp32",
269
+ "exp_avg_sq_dtype": "fp32",
270
+ "dataloader_type": "cyclic",
271
+ "manual_gc": false,
272
+ "manual_gc_interval": 0,
273
+ "lr": 1e-05,
274
+ "lr_decay_style": "cosine",
275
+ "lr_decay_iters": null,
276
+ "lr_warmup_iters": 0,
277
+ "lr_warmup_fraction": 0.03,
278
+ "min_lr": 1e-06,
279
+ "weight_decay": 0.1,
280
+ "clip_grad": 1.0,
281
+ "adam_beta1": 0.9,
282
+ "adam_beta2": 0.95,
283
+ "adam_eps": 1e-08,
284
+ "sgd_momentum": 0.9,
285
+ "save": "/data/repotune/train/outputs/mix/mix_8k_bfta_matplotlib_qwen34i_32k_2ep_v0/v0-20260122-012219",
286
+ "save_interval": 512,
287
+ "save_retain_interval": null,
288
+ "no_save_optim": true,
289
+ "no_save_rng": true,
290
+ "load": null,
291
+ "no_load_optim": false,
292
+ "no_load_rng": false,
293
+ "finetune": true,
294
+ "ckpt_format": "torch_dist",
295
+ "no_initialization": true,
296
+ "auto_detect_ckpt_format": true,
297
+ "exit_on_missing_checkpoint": true,
298
+ "async_save": false,
299
+ "use_persistent_ckpt_worker": false,
300
+ "ckpt_fully_parallel_load": false,
301
+ "ckpt_assume_constant_structure": false,
302
+ "distributed_backend": "nccl",
303
+ "local_rank": 0,
304
+ "use_distributed_optimizer": true,
305
+ "tensor_model_parallel_size": 1,
306
+ "pipeline_model_parallel_size": 1,
307
+ "decoder_first_pipeline_num_layers": null,
308
+ "decoder_last_pipeline_num_layers": null,
309
+ "account_for_embedding_in_pipeline_split": false,
310
+ "account_for_loss_in_pipeline_split": false,
311
+ "sequence_parallel": false,
312
+ "context_parallel_size": 1,
313
+ "tp_comm_overlap": false,
314
+ "overlap_grad_reduce": true,
315
+ "overlap_param_gather": true,
316
+ "distributed_timeout_minutes": 300000,
317
+ "num_layers_per_virtual_pipeline_stage": null,
318
+ "num_virtual_stages_per_pipeline_rank": null,
319
+ "microbatch_group_size_per_virtual_pipeline_stage": null,
320
+ "pipeline_model_parallel_layout": null,
321
+ "num_layers": 36,
322
+ "hidden_size": 2560,
323
+ "ffn_hidden_size": 9728,
324
+ "num_attention_heads": 32,
325
+ "group_query_attention": true,
326
+ "num_query_groups": 8,
327
+ "softmax_type": "vanilla",
328
+ "window_size": null,
329
+ "window_attn_skip_freq": null,
330
+ "max_position_embeddings": 262144,
331
+ "position_embedding_type": "rope",
332
+ "mrope_section": null,
333
+ "rotary_base": 5000000,
334
+ "rotary_percent": 1.0,
335
+ "rotary_interleaved": false,
336
+ "normalization": "RMSNorm",
337
+ "norm_epsilon": 1e-06,
338
+ "swiglu": true,
339
+ "quick_geglu": false,
340
+ "activation_func_clamp_value": null,
341
+ "glu_linear_offset": 0.0,
342
+ "untie_embeddings_and_output_weights": false,
343
+ "disable_bias_linear": true,
344
+ "add_qkv_bias": false,
345
+ "attention_dropout": 0.0,
346
+ "hidden_dropout": 0.0,
347
+ "kv_channels": 128,
348
+ "qk_layernorm": true,
349
+ "qk_l2_norm": null,
350
+ "no_rope_freq": null,
351
+ "moe_apply_probs_on_input": null,
352
+ "transformer_impl": "transformer_engine",
353
+ "num_experts": null,
354
+ "moe_layer_freq": "1",
355
+ "moe_ffn_hidden_size": null,
356
+ "moe_shared_expert_intermediate_size": null,
357
+ "moe_router_topk": 2,
358
+ "moe_router_num_groups": null,
359
+ "moe_router_group_topk": null,
360
+ "moe_router_pre_softmax": false,
361
+ "moe_router_dtype": "fp32",
362
+ "moe_router_score_function": "softmax",
363
+ "moe_router_bias_update_rate": null,
364
+ "moe_router_enable_expert_bias": false,
365
+ "moe_router_topk_scaling_factor": null,
366
+ "moe_router_load_balancing_type": "aux_loss",
367
+ "expert_model_parallel_size": 1,
368
+ "expert_tensor_parallel_size": 1,
369
+ "moe_token_dispatcher_type": null,
370
+ "moe_enable_deepep": false,
371
+ "moe_grouped_gemm": true,
372
+ "moe_permute_fusion": false,
373
+ "moe_aux_loss_coeff": 0.0,
374
+ "moe_z_loss_coeff": null,
375
+ "moe_shared_expert_overlap": false,
376
+ "moe_layer_recompute": false,
377
+ "moe_expert_capacity_factor": null,
378
+ "moe_pad_expert_input_to_capacity": false,
379
+ "moe_token_drop_policy": null,
380
+ "multi_latent_attention": false,
381
+ "q_lora_rank": null,
382
+ "kv_lora_rank": 32,
383
+ "qk_head_dim": 128,
384
+ "qk_pos_emb_head_dim": 64,
385
+ "mtp_num_layers": null,
386
+ "mtp_loss_scaling_factor": 0.1,
387
+ "fp8_format": null,
388
+ "fp8_recipe": "delayed",
389
+ "fp8_amax_history_len": 1024,
390
+ "fp8_amax_compute_algo": "max",
391
+ "fp8_param_gather": false,
392
+ "fp16": false,
393
+ "bf16": true,
394
+ "apply_query_key_layer_scaling": false,
395
+ "attention_softmax_in_fp32": true,
396
+ "log_params_norm": false,
397
+ "log_throughput": false,
398
+ "tensorboard_log_interval": 1,
399
+ "tensorboard_queue_size": 50,
400
+ "log_timers_to_tensorboard": true,
401
+ "no_log_learning_rate_to_tensorboard": false,
402
+ "log_validation_ppl_to_tensorboard": true,
403
+ "log_memory_to_tensorboard": true,
404
+ "logging_level": null,
405
+ "wandb_project": "repotune",
406
+ "wandb_exp_name": "mix_8k_bfta_matplotlib_qwen34i_32k_2ep_v0",
407
+ "wandb_save_dir": null,
408
+ "eval_iters": -1,
409
+ "eval_interval": 256,
410
+ "seq_length": 32768,
411
+ "num_workers": 16,
412
+ "no_data_sharding": false,
413
+ "megatron_extra_kwargs": {},
414
+ "add_version": true,
415
+ "rank": 0,
416
+ "global_world_size": 2,
417
+ "local_world_size": 2,
418
+ "model_suffix": "Qwen3-4B-Instruct-2507",
419
+ "model_info": "ModelInfo(model_type='qwen3_nothinking', model_dir='/root/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
420
+ "model_meta": "ModelMeta(model_type='qwen3_nothinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Instruct-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_nothinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f320c61bb00>, model_arch=None, architectures=['Qwen3MoeForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
421
+ "model_dir": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554",
422
+ "_val_dataset_exists": [
423
+ "/data/repotune/data/val/django_e13b714/sbv_msa_gemini25pro.jsonl",
424
+ "/data/repotune/data/val/django_e13b714/sbv_msa_gemini3pro.jsonl"
425
+ ],
426
+ "hub": "<class 'swift.hub.hub.HFHub'>",
427
+ "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'kimi_k2', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking', 'gpt_oss'], is_multimodal=False, bridge_cls=<class 'swift.megatron.model.gpt_bridge.GPTBridge'>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x7f312a7df600>, visual_cls=None, extra_args_provider=None)",
428
+ "extra_args": {
429
+ "model_dir": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-4B-Instruct-2507/snapshots/cdbee75f17c01a7cc42f958dc650907174af0554",
430
+ "is_multimodal": false,
431
+ "hf_model_type": "qwen3_nothinking",
432
+ "use_ray": false,
433
+ "ray_exp_name": null,
434
+ "device_groups": null,
435
+ "model": "Qwen/Qwen3-4B-Instruct-2507",
436
+ "model_type": "qwen3_nothinking",
437
+ "model_revision": null,
438
+ "task_type": "causal_lm",
439
+ "torch_dtype": "bfloat16",
440
+ "attn_impl": null,
441
+ "new_special_tokens": [],
442
+ "num_labels": null,
443
+ "problem_type": null,
444
+ "rope_scaling": null,
445
+ "device_map": null,
446
+ "max_memory": {},
447
+ "max_model_len": null,
448
+ "local_repo_path": null,
449
+ "init_strategy": null,
450
+ "template": "qwen3_nothinking",
451
+ "system": null,
452
+ "max_length": 32768,
453
+ "truncation_strategy": "left",
454
+ "max_pixels": null,
455
+ "agent_template": null,
456
+ "norm_bbox": null,
457
+ "use_chat_template": true,
458
+ "padding_free": true,
459
+ "padding_side": "right",
460
+ "sequence_parallel_size": 1,
461
+ "response_prefix": null,
462
+ "template_backend": "swift",
463
+ "dataset": [
464
+ "/data/repotune/data/agentic/bugfix/matplotlib_20201231_5b89c9c/v0/sft_all.jsonl#2048",
465
+ "/data/repotune/data/agentic/fim/matplotlib_20201231_5b89c9c/v0/sft_all.jsonl#2048",
466
+ "/data/repotune/data/agentic/testgen/matplotlib_20201231_5b89c9c/v0/sft_all.jsonl#2048",
467
+ "/data/repotune/data/agentic/ar/matplotlib_20201231_5b89c9c/sft_all.jsonl#2048"
468
+ ],
469
+ "val_dataset": [
470
+ "/data/repotune/data/val/django_e13b714/sbv_msa_gemini25pro.jsonl",
471
+ "/data/repotune/data/val/django_e13b714/sbv_msa_gemini3pro.jsonl"
472
+ ],
473
+ "cached_dataset": [],
474
+ "cached_val_dataset": [],
475
+ "split_dataset_ratio": 0.0,
476
+ "data_seed": 42,
477
+ "dataset_num_proc": 16,
478
+ "load_from_cache_file": true,
479
+ "dataset_shuffle": true,
480
+ "val_dataset_shuffle": false,
481
+ "streaming": false,
482
+ "interleave_prob": null,
483
+ "stopping_strategy": "first_exhausted",
484
+ "shuffle_buffer_size": 1000,
485
+ "download_mode": "reuse_dataset_if_exists",
486
+ "columns": {},
487
+ "strict": false,
488
+ "remove_unused_columns": true,
489
+ "model_name": null,
490
+ "model_author": null,
491
+ "custom_dataset_info": [],
492
+ "quant_method": null,
493
+ "quant_bits": null,
494
+ "hqq_axis": null,
495
+ "bnb_4bit_compute_dtype": "bfloat16",
496
+ "bnb_4bit_quant_type": "nf4",
497
+ "bnb_4bit_use_double_quant": true,
498
+ "bnb_4bit_quant_storage": null,
499
+ "max_new_tokens": null,
500
+ "temperature": null,
501
+ "top_k": 50,
502
+ "top_p": 0.9,
503
+ "repetition_penalty": 1.0,
504
+ "num_beams": 1,
505
+ "stream": false,
506
+ "stop_words": [],
507
+ "logprobs": false,
508
+ "top_logprobs": null,
509
+ "ckpt_dir": null,
510
+ "lora_modules": [],
511
+ "tuner_backend": "peft",
512
+ "train_type": "full",
513
+ "adapters": [],
514
+ "external_plugins": [],
515
+ "model_kwargs": {},
516
+ "load_args": false,
517
+ "load_data_args": false,
518
+ "packing": false,
519
+ "packing_length": null,
520
+ "packing_num_proc": 1,
521
+ "lazy_tokenize": false,
522
+ "custom_register_path": [],
523
+ "use_hf": true,
524
+ "hub_token": null,
525
+ "ddp_timeout": 18000000,
526
+ "ddp_backend": null,
527
+ "ignore_args_error": false,
528
+ "use_swift_lora": false,
529
+ "freeze_llm": false,
530
+ "freeze_vit": true,
531
+ "freeze_aligner": true,
532
+ "freeze_parameters": [],
533
+ "freeze_parameters_regex": null,
534
+ "freeze_parameters_ratio": 0.0,
535
+ "trainable_parameters": [],
536
+ "trainable_parameters_regex": null,
537
+ "adapter_load": null,
538
+ "target_modules": [
539
+ "all-linear"
540
+ ],
541
+ "target_regex": null,
542
+ "modules_to_save": [],
543
+ "lora_rank": 8,
544
+ "lora_alpha": 32,
545
+ "lora_dropout": 0.05,
546
+ "lora_bias": "none",
547
+ "lora_dtype": null,
548
+ "use_rslora": false,
549
+ "rlhf_type": null,
550
+ "ref_load": null,
551
+ "ref_adapter_load": null,
552
+ "beta": 0.1,
553
+ "rpo_alpha": null,
554
+ "reference_free": false,
555
+ "label_smoothing": 0.0,
556
+ "f_divergence_type": "reverse_kl",
557
+ "loss_type": null,
558
+ "desirable_weight": 1.0,
559
+ "undesirable_weight": 1.0,
560
+ "calculate_KL": null,
561
+ "center_rewards_coefficient": null,
562
+ "generation_batch_size": null,
563
+ "steps_per_generation": null,
564
+ "num_generations": 8,
565
+ "num_generations_eval": null,
566
+ "max_completion_length": 512,
567
+ "importance_sampling_level": "token",
568
+ "tau_pos": 1.0,
569
+ "tau_neg": 1.05,
570
+ "epsilon": 0.2,
571
+ "epsilon_high": null,
572
+ "delta": null,
573
+ "use_vllm": true,
574
+ "vllm_mode": null,
575
+ "vllm_enable_prefix_caching": true,
576
+ "vllm_gpu_memory_utilization": 0.9,
577
+ "vllm_tensor_parallel_size": 1,
578
+ "vllm_max_model_len": null,
579
+ "vllm_enforce_eager": false,
580
+ "vllm_limit_mm_per_prompt": null,
581
+ "vllm_disable_cascade_attn": false,
582
+ "vllm_max_num_seqs": null,
583
+ "vllm_mm_processor_cache_gb": null,
584
+ "vllm_engine_kwargs": null,
585
+ "sleep_level": 0,
586
+ "offload_optimizer": false,
587
+ "offload_model": false,
588
+ "offload_bridge": false,
589
+ "vllm_server_base_url": null,
590
+ "vllm_server_host": null,
591
+ "vllm_server_port": [
592
+ 8000
593
+ ],
594
+ "vllm_server_timeout": 240.0,
595
+ "vllm_server_group_port": null,
596
+ "reward_funcs": [],
597
+ "reward_weights": null,
598
+ "cosine_min_len_value_wrong": -0.5,
599
+ "cosine_max_len_value_wrong": 0.0,
600
+ "cosine_min_len_value_correct": 1.0,
601
+ "cosine_max_len_value_correct": 0.5,
602
+ "cosine_max_len": null,
603
+ "repetition_n_grams": 3,
604
+ "repetition_max_penalty": -1.0,
605
+ "soft_max_length": null,
606
+ "soft_cache_length": null,
607
+ "dynamic_sample": false,
608
+ "max_resample_times": 3,
609
+ "overlong_filter": false,
610
+ "scale_rewards": "group",
611
+ "advantage_estimator": "grpo",
612
+ "kl_in_reward": false,
613
+ "wandb_log_unique_prompts": null,
614
+ "log_completions": false,
615
+ "rollout_importance_sampling_mode": null,
616
+ "rollout_importance_sampling_threshold": 2.0,
617
+ "log_rollout_offpolicy_metrics": false,
618
+ "off_policy_sequence_mask_delta": null,
619
+ "reward_model": null,
620
+ "reward_model_plugin": null,
621
+ "sync_ref_model": false,
622
+ "ref_model_sync_steps": 512,
623
+ "ref_model_mixup_alpha": 0.6,
624
+ "async_generate": false,
625
+ "move_model_batches": null,
626
+ "multi_turn_scheduler": null,
627
+ "max_turns": null,
628
+ "completion_length_limit_scope": "per_round",
629
+ "vllm_server_pass_dataset": false,
630
+ "log_entropy": false,
631
+ "top_entropy_quantile": 1.0,
632
+ "num_iterations": 1,
633
+ "check_model": true,
634
+ "padded_vocab_size": 151936,
635
+ "initialize_embedding": false,
636
+ "mlp_padding_free": false,
637
+ "load_safetensors": true,
638
+ "save_safetensors": true,
639
+ "ref_model": null,
640
+ "ref_adapters": [],
641
+ "merge_lora": true,
642
+ "max_shard_size": "5GB",
643
+ "train_dataloader_shuffle": true,
644
+ "dataloader_pin_memory": true,
645
+ "dataloader_persistent_workers": true,
646
+ "dataloader_prefetch_factor": 10,
647
+ "architectures": "Qwen3ForCausalLM",
648
+ "llm_architectures": "Qwen3ForCausalLM",
649
+ "max_epochs": 2,
650
+ "enable_dft_loss": false,
651
+ "enable_channel_loss": false,
652
+ "save_strategy": "steps",
653
+ "original_max_position_embeddings": null,
654
+ "partial_rotary_factor": null,
655
+ "use_shared_expert_gate": false,
656
+ "vit_gradient_checkpointing": true,
657
+ "vit_lr": null,
658
+ "aligner_lr": null,
659
+ "gradient_checkpointing_kwargs": null,
660
+ "linear_num_value_heads": null,
661
+ "linear_num_key_heads": null,
662
+ "linear_key_head_dim": null,
663
+ "linear_value_head_dim": null,
664
+ "linear_conv_kernel_dim": null,
665
+ "layer_types": null,
666
+ "mrope_interleaved": false,
667
+ "add_version": true
668
+ }
669
+ }
chat_template.jinja ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
27
+ {%- if message.tool_calls %}
28
+ {%- for tool_call in message.tool_calls %}
29
+ {%- if (loop.first and content) or (not loop.first) %}
30
+ {{- '\n' }}
31
+ {%- endif %}
32
+ {%- if tool_call.function %}
33
+ {%- set tool_call = tool_call.function %}
34
+ {%- endif %}
35
+ {{- '<tool_call>\n{"name": "' }}
36
+ {{- tool_call.name }}
37
+ {{- '", "arguments": ' }}
38
+ {%- if tool_call.arguments is string %}
39
+ {{- tool_call.arguments }}
40
+ {%- else %}
41
+ {{- tool_call.arguments | tojson }}
42
+ {%- endif %}
43
+ {{- '}\n</tool_call>' }}
44
+ {%- endfor %}
45
+ {%- endif %}
46
+ {{- '<|im_end|>\n' }}
47
+ {%- elif message.role == "tool" %}
48
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
49
+ {{- '<|im_start|>user' }}
50
+ {%- endif %}
51
+ {{- '\n<tool_response>\n' }}
52
+ {{- content }}
53
+ {{- '\n</tool_response>' }}
54
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
55
+ {{- '<|im_end|>\n' }}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- endfor %}
59
+ {%- if add_generation_prompt %}
60
+ {{- '<|im_start|>assistant\n' }}
61
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 262144,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "pad_token_id": 151643,
60
+ "rms_norm_eps": 1e-06,
61
+ "rope_scaling": null,
62
+ "rope_theta": 5000000,
63
+ "sliding_window": null,
64
+ "tie_word_embeddings": true,
65
+ "transformers_version": "4.57.3",
66
+ "use_cache": true,
67
+ "use_sliding_window": false,
68
+ "vocab_size": 151936
69
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:110990f6ac35f387387a1dfc3a0b751bd4e57ff6db76f39514ab78fae4ba3b8e
3
+ size 4967220560
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12705b8d039a938a235c0100c1ac7512d4f77f254dbf5305529f40398ed35821
3
+ size 3077761384
model.safetensors.index.json ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8044936192
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
266
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
269
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
341
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
343
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
370
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
372
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
374
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
376
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
377
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
378
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
379
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
380
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
381
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
382
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
383
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
384
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
385
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
386
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
387
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
388
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
389
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
390
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
391
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
392
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
393
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
394
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
395
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
396
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
397
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
398
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
399
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
400
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
401
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
402
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
403
+ "model.norm.weight": "model-00002-of-00002.safetensors"
404
+ }
405
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1010000,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff